update new model

added_tokens.json

@@ -1,4 +0,0 @@
-{
-  "<|im_end|>": 32000,
-  "<|im_start|>": 32001
-}

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "./Mistral-7B",
   "architectures": [
     "MistralForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -18,8 +18,8 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.2",
-  "use_cache": false,
-  "vocab_size": 32002
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.35.2"
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
 }

tokenizer.model → model-00001-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:18d48a4beb520d2a36ea08e6dcf7e256670ec2070daebcee6eea8648b9a82789
+size 899696312

model-00001-of-00003.safetensors → model-00002-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4fd712b582f46ee088768d407c38e0781fde96a3c3848d4493c88a5431d7699
-size 4943178720
+oid sha256:3dbccbc82077982f3b88414152a582d06ca3fc7df006589e4fd107910f8ad3a6
+size 989890680

model-00002-of-00003.safetensors → model-00003-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a271f620dd35a301e614a99ef2b710ee3c1a324f0acabf10f380ca0baecf86a
-size 4999819336
+oid sha256:6ef55fdd9e7181d7e906bfba952ef9774e03585d14484f73b8355a86b78652c9
+size 989907288

model-00003-of-00003.safetensors → model-00004-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bc6883300eda0170fde19acbf43ad49d070638265c963ec4624fcc67c1ec42
-size 4540532728
+oid sha256:d22b2e4353a2dbf3c5fd785eb5d7b5eb06c5e4710017fa14e84e798fe1dc8c67
+size 956336592

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a01d57857249ef59ba74b4f2bfcb741f1695fb7f3dff78da340cd22640c3e7f
+size 989890696

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e953ae02ae3abfd86436286ee8715a2a11106722125808195a76be50765bc3
+size 989890696

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a4896295c37532605d5ea59ac2c982ff45a3b85c373c13b482463a2807e1c2
+size 989907312

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d87e277f2e49cae13056b7841662d5f750f1ba8d41e2b051a9344116b5bebe
+size 956336616

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0ca5ad5ed1536f31c91c32392a850a5fc45386c11f8ced9816757475c653ed
+size 989890696

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f5003bcdbe719cb59ca9e258be51f045e6cfb2e180ea16224a432b9a46bb0d
+size 989890696

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43821e31e32a1cb6b97465bb408713d7095b5ed1f736d3c3148b9b0b4e392121
+size 989907312

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5005e8f7ae53ef1c7fd66b5853ad37725b5a9a8448acc9865514faeabfc531
+size 956336616

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fe30fe8b051a256eb66eb7e96ca045ddf773e8b8755e195ee5db7abdf1ddc4
+size 989890696

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6303526f7675217eee182c14bfc9d68e9d18ba8169bfcf332296c12d8fff5f
+size 989890696

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31507507d762948b8f4d62481cc1bbc1260c547d53b04d92ea21e5931b7f119d
+size 815834664

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 14483496960
+    "total_size": 14483464192
   },
   "weight_map": {
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
   }
 }

special_tokens_map.json

@@ -1,7 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<unk>",
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -29,24 +29,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32000,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32001,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -23,37 +25,24 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "use_default_system_prompt": true
 }